Gemma 4 31B
on NVIDIA DGX Spark · llama.cpp
Oct 9, 2026
Summary
User reports Gemma 4 31B at about 6.0 t/s on a DGX Spark without MTP, and 11.4 to 19.3 t/s with MTP speculative decoding enabled (--spec-draft-n-max 4).
Setup is llama.cpp with the am17an/Gemma4-31B-it-GGUF build.
With MTP the draft accept rate was 0.5881 over 9 requests.
The user notes no speed-up for the MoE variant, over 2x average speedup on the dense model, and that AIME-26 results (~87%) were replicated.